{"total":195,"rows":[{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210,"area":"lr"},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763,"area":null},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535,"area":null},{"id":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417,"area":"synth"},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247,"area":"alignment"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2506.21734","title":"Hierarchical Reasoning Model","created":"2025-06-26","cited_by_count":177,"area":"lr"},{"id":"2505.24760","title":"REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards","created":"2025-05-30","cited_by_count":130,"area":null},{"id":"2311.09807","title":"The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text","created":"2023-11-16","cited_by_count":100,"area":null},{"id":"2305.13230","title":"To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis","created":"2023-05-22","cited_by_count":92,"area":"moe"},{"id":"2306.15546","title":"When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directions","created":"2023-06-27","cited_by_count":84,"area":null},{"id":"2502.12118","title":"Scaling Test-Time Compute Without Verification or RL is Suboptimal","created":"2025-02-17","cited_by_count":84,"area":"lr"},{"id":"2506.10943","title":"Self-Adapting Language Models","created":"2025-06-12","cited_by_count":84,"area":null},{"id":"2311.16822","title":"Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop","created":"2023-11-28","cited_by_count":79,"area":null},{"id":"2309.16575","title":"A Benchmark for Learning to Translate a New Language from One Grammar Book","created":"2023-09-28","cited_by_count":75,"area":null},{"id":"2507.22062","title":"Meta CLIP 2: A Worldwide Scaling Recipe","created":"2025-07-29","cited_by_count":64,"area":"mllm"},{"id":"2507.15857","title":"Diffusion Beats Autoregressive in Data-Constrained Settings","created":"2025-07-21","cited_by_count":63,"area":"diffusion"},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60,"area":null},{"id":"2410.15226","title":"On the Diversity of Synthetic Data and its Impact on Training Large Language Models","created":"2024-10-19","cited_by_count":59,"area":"synth"},{"id":"2312.06353","title":"Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes","created":"2023-12-11","cited_by_count":55,"area":null},{"id":"2402.02622","title":"DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging","created":"2024-02-04","cited_by_count":53,"area":null},{"id":"2505.20347","title":"SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data","created":"2025-05-25","cited_by_count":51,"area":"lr"},{"id":"2503.18866","title":"Reasoning to Learn from Latent Thoughts","created":"2025-03-24","cited_by_count":45,"area":"lr"},{"id":"2509.07414","title":"Language Self-Play For Data-Free Training","created":"2025-09-09","cited_by_count":43,"area":"synth"},{"id":"2501.02497","title":"A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning","created":"2025-01-05","cited_by_count":40,"area":"lr"},{"id":"2502.19249","title":"Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases","created":"2025-02-26","cited_by_count":37,"area":null},{"id":"2502.14425","title":"A Survey on Data Contamination for Large Language Models","created":"2025-02-20","cited_by_count":35,"area":null},{"id":"2503.03150","title":"Position: Model Collapse Does Not Mean What You Think","created":"2025-03-05","cited_by_count":33,"area":"synth"},{"id":"2311.09227","title":"Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives","created":"2023-09-29","cited_by_count":31,"area":null},{"id":"2505.10475","title":"Parallel Scaling Law for Language Models","created":"2025-05-15","cited_by_count":30,"area":"lr"},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2506.15674","title":"Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers","created":"2025-06-18","cited_by_count":28,"area":"lr"},{"id":"2408.11304","title":"FedMoE: Personalized Federated Learning via Heterogeneous Mixture of Experts","created":"2024-08-21","cited_by_count":27,"area":"moe"},{"id":"2404.09173","title":"TransformerFAM: Feedback attention is working memory","created":"2024-04-14","cited_by_count":22,"area":null},{"id":"2602.05400","title":"OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration","created":"2026-02-05","cited_by_count":21,"area":null},{"id":"2405.15815","title":"A social path to human-like artificial intelligence","created":"2024-05-22","cited_by_count":20,"area":null},{"id":"2505.10717","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","created":"2025-05-15","cited_by_count":20,"area":"alignment"},{"id":"2505.23725","title":"MuLoCo: Muon is a practical inner optimizer for DiLoCo","created":"2025-05-29","cited_by_count":18,"area":null},{"id":"2405.05990","title":"Special Characters Attack: Toward Scalable Training Data Extraction From Large Language Models","created":"2024-05-09","cited_by_count":17,"area":null},{"id":"2504.12427","title":"Position: The Most Expensive Part of an LLM should be its Training Data","created":"2025-04-16","cited_by_count":16,"area":null},{"id":"2509.23184","title":"PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space","created":"2025-09-27","cited_by_count":16,"area":"lr"},{"id":"2305.12563","title":"A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers","created":"2023-05-21","cited_by_count":15,"area":"lr"},{"id":"2311.01550","title":"Market Concentration Implications of Foundation Models","created":"2023-11-02","cited_by_count":15,"area":null},{"id":"2410.01720","title":"Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective","created":"2024-10-02","cited_by_count":15,"area":"synth"},{"id":"2504.00509","title":"Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?","created":"2025-04-01","cited_by_count":15,"area":"lr"},{"id":"2505.14733","title":"The Energy Cost of Reasoning: Analyzing Energy Usage in LLMs with Test-time Compute","created":"2025-05-20","cited_by_count":15,"area":"lr"},{"id":"2603.10055","title":"Training Language Models via Neural Cellular Automata","created":"2026-03-09","cited_by_count":15,"area":null},{"id":"2309.07207","title":"EarthPT: a time series foundation model for Earth Observation","created":"2023-09-13","cited_by_count":14,"area":null},{"id":"2405.10799","title":"Training Compute Thresholds: Features and Functions in AI Regulation","created":"2024-05-17","cited_by_count":14,"area":null},{"id":"2507.13966","title":"Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need","created":"2025-07-18","cited_by_count":13,"area":"lr"},{"id":"2508.09494","title":"Learning Facts at Scale with Active Reading","created":"2025-08-13","cited_by_count":13,"area":null},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2402.14270","title":"Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization","created":"2024-02-22","cited_by_count":12,"area":null},{"id":"2502.00372","title":"NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning","created":"2025-02-01","cited_by_count":12,"area":"lr"},{"id":"2506.22696","title":"Residual Matrix Transformers: Scaling the Size of the Residual Stream","created":"2025-06-28","cited_by_count":12,"area":null},{"id":"2602.11698","title":"SpiralFormer: Looped Transformers Can Learn Hierarchical Dependencies via Multi-Resolution Recursion","created":"2026-02-12","cited_by_count":12,"area":null},{"id":"2608.19197","title":"SPADE: Self-Play in Adaptive Synthetic Executable Environments","created":"2026-08-19","cited_by_count":12,"area":"synth"},{"id":"2506.02961","title":"FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models","created":"2025-06-03","cited_by_count":11,"area":null},{"id":"2608.20318","title":"AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement","created":"2026-08-20","cited_by_count":11,"area":"agents"},{"id":"2408.11851","title":"SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red Teaming","created":"2024-08-14","cited_by_count":10,"area":"safety"},{"id":"2502.18099","title":"Stackelberg Self-Annotation: A Robust Approach to Data-Efficient LLM Alignment","created":"2025-02-25","cited_by_count":10,"area":"alignment"},{"id":"2504.12563","title":"MetaSynth: Meta-Prompting-Driven Agentic Scaffolds for Diverse Synthetic Data Generation","created":"2025-04-17","cited_by_count":10,"area":"agents"},{"id":"2509.24771","title":"LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space","created":"2025-09-29","cited_by_count":9,"area":"lr"},{"id":"2309.08589","title":"Chain-of-Thought Reasoning is a Policy Improvement Operator","created":"2023-09-15","cited_by_count":8,"area":"lr"},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2410.20796","title":"Rephrasing natural text data with different languages and quality levels for Large Language Model pre-training","created":"2024-10-28","cited_by_count":8,"area":null},{"id":"2502.01697","title":"BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation","created":"2025-02-03","cited_by_count":8,"area":"synth"},{"id":"2505.20325","title":"Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence","created":"2025-05-23","cited_by_count":8,"area":"lr"},{"id":"2507.14240","title":"HuggingGraph: Understanding the Supply Chain of LLM Ecosystem","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2510.04071","title":"What Makes Diffusion Language Models Super Data Learners?","created":"2025-10-05","cited_by_count":8,"area":"diffusion"},{"id":"2510.07739","title":"MeSH: Memory-as-State-Highways for Recursive Transformers","created":"2025-10-09","cited_by_count":8,"area":null},{"id":"2605.19407","title":"A Bitter Lesson for Data Filtering","created":"2026-05-19","cited_by_count":8,"area":null},{"id":"2310.14579","title":"FedSplitX: Federated Split Learning for Computationally-Constrained Heterogeneous Clients","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2502.13247","title":"Grounding LLM Reasoning with Knowledge Graphs","created":"2025-02-18","cited_by_count":7,"area":"lr"},{"id":"2603.18534","title":"Data-efficient pre-training by scaling synthetic megadocs","created":"2026-03-19","cited_by_count":7,"area":null},{"id":"2501.07314","title":"FinerWeb-10BT: Refining Web Data with LLM-Based Line-Level Filtering","created":"2025-01-13","cited_by_count":6,"area":null},{"id":"2506.15690","title":"LLM Web Dynamics: Tracing Model Collapse in a Network of LLMs","created":"2025-05-26","cited_by_count":6,"area":"synth"},{"id":"2508.14927","title":"AI Testing Should Account for Sophisticated Strategic Behaviour","created":"2025-08-19","cited_by_count":6,"area":null},{"id":"2509.15248","title":"Synthetic bootstrapped pretraining","created":"2025-09-17","cited_by_count":6,"area":"synth"},{"id":"2510.10681","title":"RePro: Training Language Models to Faithfully Recycle the Web for Pretraining","created":"2025-10-12","cited_by_count":6,"area":null},{"id":"2605.14389","title":"Nexus : An Agentic Framework for Time Series Forecasting","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2307.06933","title":"FDAPT: Federated Domain-adaptive Pre-training for Language Models","created":"2023-07-12","cited_by_count":5,"area":null},{"id":"2402.14652","title":"Cleaner Pretraining Corpus Curation with Neural Web Scraping","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2412.13860","title":"Domain-adaptative Continual Learning for Low-resource Tasks: Evaluation on Nepali","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2502.15850","title":"Forecasting Frontier Language Model Agent Capabilities","created":"2025-02-21","cited_by_count":5,"area":"agents"},{"id":"2503.01630","title":"Machine Learners Should Acknowledge the Legal Implications of Large Language Models as Personal Data","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2504.13123","title":"Low-hallucination Synthetic Captions for Large-Scale Vision-Language Model Pre-training","created":"2025-04-17","cited_by_count":5,"area":"mllm"},{"id":"2505.00985","title":"Position: Enough of Scaling LLMs! Lets Focus on Downscaling","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2505.11730","title":"Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling","created":"2025-05-16","cited_by_count":5,"area":"lr"},{"id":"2505.15508","title":"Multilingual Test-Time Scaling via Initial Thought Transfer","created":"2025-05-21","cited_by_count":5,"area":"lr"},{"id":"2506.20057","title":"Universal pre-training by iterated random computation","created":"2025-06-24","cited_by_count":5,"area":null},{"id":"2508.03097","title":"VFLAIR-LLM: A Comprehensive Framework and Benchmark for Split Learning of LLMs","created":"2025-08-05","cited_by_count":5,"area":null},{"id":"2509.18083","title":"Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning","created":"2025-09-22","cited_by_count":5,"area":"lr"},{"id":"2604.20051","title":"Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text","created":"2026-04-21","cited_by_count":5,"area":"synth"},{"id":"2311.05020","title":"First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models","created":"2023-11-08","cited_by_count":4,"area":null},{"id":"2403.04529","title":"Enhancing Data Quality in Federated Fine-Tuning of Foundation Models","created":"2024-03-07","cited_by_count":4,"area":null},{"id":"2405.09597","title":"When AI Eats Itself: On the Caveats of AI Autophagy","created":"2024-05-15","cited_by_count":4,"area":null},{"id":"2408.00307","title":"ABC Align: Large Language Model Alignment for Safety & Accuracy","created":"2024-08-01","cited_by_count":4,"area":"alignment"}],"next_cursor":"100"}